Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2201 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5275. Min Range: -5.5275
Max Act: 5.5275. Min Act: -0.1700
Data Index: 7013599 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5275. Min Range: -5.5275
Max Act: 5.5275. Min Act: -0.1700
Data Index: 4978389 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5275. Min Range: -5.5275
Max Act: 5.4650. Min Act: -0.1700
Data Index: 8723769 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5275. Min Range: -5.5275
Max Act: 5.4337. Min Act: -0.1700
Data Index: 8029541 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5275. Min Range: -5.5275
Max Act: 5.4337. Min Act: -0.1700
Data Index: 6262606 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5275. Min Range: -5.5275
Max Act: 5.4025. Min Act: -0.1700
Data Index: 4498826 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5275. Min Range: -5.5275
Max Act: 5.4025. Min Act: -0.1700
Data Index: 7250107 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5275. Min Range: -5.5275
Max Act: 5.3712. Min Act: -0.1700
Data Index: 2026989 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5275. Min Range: -5.5275
Max Act: 5.4025. Min Act: -0.1700
Data Index: 6678827 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5275. Min Range: -5.5275
Max Act: 5.3712. Min Act: -0.1700
Data Index: 921768 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5275. Min Range: -5.5275
Max Act: 5.3712. Min Act: -0.1700
Data Index: 1575360 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5275. Min Range: -5.5275
Max Act: 5.3712. Min Act: -0.1700
Data Index: 4683691 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5275. Min Range: -5.5275
Max Act: 5.3712. Min Act: -0.1700
Data Index: 714238 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5275. Min Range: -5.5275
Max Act: 5.3712. Min Act: -0.1700
Data Index: 8236887 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5275. Min Range: -5.5275
Max Act: 5.4025. Min Act: -0.1700
Data Index: 1721957 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5275. Min Range: -5.5275
Max Act: 5.3712. Min Act: -0.1700
Data Index: 3684498 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5275. Min Range: -5.5275
Max Act: 5.3400. Min Act: -0.1700
Data Index: 2654025 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5275. Min Range: -5.5275
Max Act: 5.3400. Min Act: -0.1700
Data Index: 2801827 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5275. Min Range: -5.5275
Max Act: 5.3400. Min Act: -0.1700
Data Index: 1993899 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5275. Min Range: -5.5275
Max Act: 5.3400. Min Act: -0.1700
Data Index: 7437000 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #19